Lightweight ML-based Runtime Prefetcher Selection on Many-core Platforms

Erika S Alcorta, Neeraja J. Yadwadkar, Andreas Gerstlauer

Keywords: runtime systems, prefetcher selection, many-core

TL;DR: We propose a lightweight supervised learning model to manage composite prefetchers in many0core systems that improves the performance of unseen workloads by up to 25% and by 2.7\% on average over the default prefetcher configuration.

Abstract: Modern computer designs support composite prefetching, where multiple individual prefetcher components are used to target different memory access patterns. However, multiple prefetchers competing for resources can drastically hurt performance, especially in many-core systems where cache and other resources are shared and very limited. Prior work has proposed mitigating this issue by selectively enabling and disabling prefetcher components during runtime. Traditional approaches proposed heuristics that are hard to scale with increasing core and prefetcher component counts. More recently, deep reinforcement learning was proposed. However, it is too expensive to deploy in real-world many-core systems. In this work, we propose a new phase-based methodology for training a lightweight supervised learning model to manage composite prefetchers. Our approach improves the performance of a state-of-the-art many-core system by up to 25\% and by 2.7\% on average over its default prefetcher configuration.

Workshop Track: MLArchSys

Presentation: In-Person

Presenter Full Name: Erika Susana Alcorta

Presenter Email: [e-mail]

Presenter Bio: Erika Susana Alcorta received the M.S. degree in Electrical and Computer Engineering from The University of Texas at Austin (UT) in 2019, where she is currently working toward the Ph.D. degree. Prior to joining UT Austin, she has 4 years of industry experience as a software engineer. Her current research interests include applications of machine learning to computer systems design and ML acceleration with limited resources.